LLMs, especially GPT-4, can classify SQL query equivalence on complex real-world assignment queries far beyond formal tools' coverage, but they systematically over-predict equivalence.
Chandra and Philip M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can the Rookies Cut the Tough Cookie? Exploring the Use of LLMs for SQL Equivalence Checking
LLMs, especially GPT-4, can classify SQL query equivalence on complex real-world assignment queries far beyond formal tools' coverage, but they systematically over-predict equivalence.